Advancing Image-Based Grapevine Variety Classification with a New Benchmark and Evaluation of Masked Autoencoders

TL;DR

This paper evaluates Masked Autoencoders for grapevine variety classification using a new benchmark dataset, demonstrating improved performance and insights into training strategies and model robustness across seasons.

Contribution

It introduces two comprehensive benchmarks for grapevine variety classification and analyzes the effectiveness of MAEs in this agricultural imaging context, highlighting their advantages over transfer learning.

Findings

MAE-pretrained ViT-B/16 achieved an F1 score of 0.7956

Long pre-training enhances model performance

Simple data augmentation outperforms complex methods

Abstract

Grapevine varieties are essential for the economies of many wine-producing countries, influencing the production of wine, juice, and the consumption of fruits and leaves. Traditional identification methods, such as ampelography and molecular analysis, have limitations: ampelography depends on expert knowledge and is inherently subjective, while molecular methods are costly and time-intensive. To address these limitations, recent studies have applied deep learning (DL) models to classify grapevine varieties using image data. However, due to the small dataset sizes, these methods often depend on transfer learning from datasets from other domains, e.g., ImageNet1K (IN1K), which can lead to performance degradation due to domain shift and supervision collapse. In this context, self-supervised learning (SSL) methods can be a good tool to avoid this performance degradation, since they can learn directly from data, without external labels. This study presents an evaluation of Masked Autoencoders (MAEs) for identifying grapevine varieties based on field-acquired images. The main contributions of this study include two benchmarks comprising 43 grapevine varieties collected across different seasons, an analysis of MAE's application in the agricultural context, and a performance comparison of trained models across seasons. Our results show that a ViT-B/16 model pre-trained with MAE and the unlabeled dataset achieved an F1 score of 0.7956, outperforming all other models. Additionally, we observed that pre-trained models benefit from long pre-training, perform well under low-data training regime, and that simple data augmentation methods are more effective than complex ones. The study also found that the mask ratio in MAE impacts performance only marginally.